DMGAN: Discriminative Metric-based Generative Adversarial Networks

Abstract With the proposed of Generative Adversarial Networks (GANs), the generative adversarial models have been extensively studied in recent years. Although probability-based methods have achieved remarkable results in image synthesis tasks, there are still some unsolved challenges that are difficult to overcome. In this paper, we propose a novel model, called Discriminative Metric-based Generative Adversarial Networks (DMGANs), for generating real-like samples from the perspective of deep metric learning. To be specific, the generator is trained to generate realistic samples by reducing the distance between real and generated samples. Instead of outputting probability, the discriminator in our model is conducted as a feature extractor, which is well constrained by introducing a combination of identity preserving loss and discriminative loss. Meanwhile, to reduce the identity preserving loss, we calculate the distance between samples and their corresponding center and update these centers during training to improve the stability of our model. In addition, a data-dependent strategy of weight adaption is proposed to further improve the quality of generated samples. Experiments on several datasets illustrate the potential of our model.

[1]  Xin Yao,et al.  Evolutionary Generative Adversarial Networks , 2018, IEEE Transactions on Evolutionary Computation.

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[4]  Sungroh Yoon,et al.  How Generative Adversarial Networks and Their Variants Work , 2017, ACM Comput. Surv..

[5]  Yi Fang,et al.  Metric-based Generative Adversarial Network , 2017, ACM Multimedia.

[6]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[7]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[8]  Yiannis Demiris,et al.  MAGAN: Margin Adaptation for Generative Adversarial Networks , 2017, ArXiv.

[9]  Manohar Paluri,et al.  Metric Learning with Adaptive Density Discrimination , 2015, ICLR.

[10]  Richard S. Zemel,et al.  Generative Moment Matching Networks , 2015, ICML.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[13]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[14]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[15]  Xiaohua Zhai,et al.  A Large-Scale Study on Regularization and Normalization in GANs , 2018, ICML.

[16]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[17]  Zi-Yi Dou.  Metric Learning-based Generative Adversarial Network , 2017, ArXiv.

[18]  Ce Wang,et al.  Label-Removed Generative Adversarial Networks Incorporating with K-Means , 2019, Neurocomputing.

[19]  Yoshua Bengio,et al.  Deep Generative Stochastic Networks Trainable by Backprop , 2013, ICML.

[20]  Yi Peng,et al.  Soft consensus cost models for group decision making and economic interpretations , 2019, Eur. J. Oper. Res..

[21]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[22]  Yi Peng,et al.  Evaluation of clustering algorithms for financial risk analysis using MCDM methods , 2014, Inf. Sci..

[23]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.

[24]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[25]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[26]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[27]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[28]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[29]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[30]  Phillip Isola,et al.  On the "steerability" of generative adversarial networks , 2019, ICLR.

[31]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[32]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[33]  Yi Peng,et al.  A Group Decision Making Model for Integrating Heterogeneous Information , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[34]  Bo Zhang,et al.  Recent Advances of Generative Adversarial Networks in Computer Vision , 2019, IEEE Access.

[35]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.

[36]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.